USAGE MODELING

• US 20150371023A1
• Filed: 03/12/2014
• Published: 12/24/2015
• Est. Priority Date: 03/13/2013
• Status: Abandoned Application

• Current Assignee: University of Pittsburgh of The Commonwealth System of Higher Education
• Original Assignee: University of Pittsburgh of The Commonwealth System of Higher Education
• Inventors: Mao, Zhi-Hong, Chen, Yiran, Nixon, Kent W.
• Application Number:
  US14/767,485
• Publication Number:
  US 20150371023A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Embodiments of techniques or systems for usage modeling or gesture based authentication are provided herein. Actions of a user may be captured, classified, and utilized to generate an authentication scheme for a device based on gesture recognition, gesture analysis, or action analysis. Training data may be determined based on actions deemed to be training actions and one or more action models may be generated based on the training data. An action model may be indicative of how a user performs a particular or predetermined action. When a security mode is enabled, usage actions may be recorded and usage data may be extracted or determined based on the usage actions. A usage action may be identified and corresponding usage data may be compared with training data from an appropriate action model. An identity of a user associated with the usage action may be determined based on this comparison.

Claims

1. A method for usage modeling, comprising:

receiving one or more usage actions between a user and a device;

comparing one or more of the usage actions with a corresponding action model; and

authenticating the user based on a match between one or more of the usage actions and the corresponding action model, wherein the receiving, the comparing, or the authenticating is implemented via a processing unit.

2. The method of claim 1, comprising identifying one or more of the usage actions.

3. The method of claim 2, comprising selecting the corresponding action model based on identification of one or more of the usage actions.

4. The method of claim 1, wherein one or more of the usage actions is associated with usage data.

5. The method of claim 1, wherein the corresponding action model is associated with training data indicative of one or more training actions between an authorized user and the device.

6. The method of claim 1, wherein comparing one or more of the usage actions with the corresponding action model comprises comparing usage data of one or more of the usage actions with training data of the corresponding action model.

7. The method of claim 1, wherein the corresponding action model is indicative of how an authorized user interacts with the device for a corresponding action.

8. The method of claim 1, comprising providing access to one or more portions of the device based on determining the match between one or more of the usage actions and the corresponding action model.

9. The method of claim 1, comprising denying access to one or more portions of the device based on a difference between one or more of the usage actions and the corresponding action model.

10. The method of claim 1, comprising notifying one or more parties based on a threshold difference between one or more of the usage actions and the corresponding action model.

11. A system for usage modeling, comprising:

a monitoring component for capturing one or more actions between one or more users and a device;

a learning component for building one or more action models based on one or more training actions of one or more of the actions; and

a database component for storing one or more of the action models, wherein the monitoring component, the learning component, or the database component is implemented via a processing unit.

12. The system of claim 11, wherein the monitoring component calculates training data for one or more of the training actions captured by the monitoring component during a training mode, wherein one or more of the training actions is between an authorized user and the device.

13. The system of claim 11, wherein the monitoring component calculates usage data for one or more usage actions captured by the monitoring component during a usage mode, wherein one or more of the usage action is between a user and the device.

14. The system of claim 13, comprising a matching component for comparing the usage data with training data from one or more of the action models.

15. The system of claim 14, wherein the matching component determines an identity of the user based on the comparison between the usage data and the training data.

16. The system of claim 14, comprising a security component for providing one or more response actions based on the comparison between the usage data and the training data.

17. A computer-readable storage medium comprising computer-executable instructions, which when executed via a processing unit on a computer performs acts, comprising:

capturing training data indicative of one or more training actions between an authorized user and a device;

generating one or more action models based on the training data;

receiving usage data indicative of one or more usage actions between a user and the device; and

providing a response action based on one or more of the action models and the usage data.

18. The computer-readable storage medium of claim 17, wherein the response action comprises granting access to the device or denying access to the device.

19. The computer-readable storage medium of claim 17, wherein the response action comprises notifying one or more parties based on a difference between the usage data and training data of one or more of the action models.

20. The computer-readable storage medium of claim 17, wherein one or more of the action models is indicative of how the authorized user interacts with the device for one or more respective actions.